Verify images with Zapier and Peltarion

Build an automated and effective system that verifies customer photo uploads.

Put yourself in the shoes of a car insurer. They receive a lot of insurance claims from their customers, and the insurer must ensure that every customer’s car is in fact damaged before paying any money. This is a tedious task but luckily a task that can be automated.

In this tutorial, we’ll show you how to set up a verification system that uses the customer’s information and image and then notifies systems administrators when something is wrong.

12 - Target audience: Intermediate users
12 - Estimated time: 15 minutes

You will learn
12 - Build a Zapier workflow
12 - Connect Peltarion to a Zapier workflow

Zapier tutorial workflow
Figure 1. Zapier tutorial workflow

Create a spreadsheet with insurance claims

Make your own copy of this spreadsheet with insurance claims that we’ve made. The spreadsheet includes information on each claim. Most importantly, it contains a link to a photo for each claim. You will use this photo in a Peltarion classification model.

Tips on tools for survey collection

You can also create your own spreadsheet that includes a photo for each claim. This photo must have a link so the Peltarion classification model can use it.

We used Typeform to set up a form that, from a chatwindow, collected dummy-information about insurance claims from customers. You could also try AirTable, which also worked very well and, as an added benefit, also removes the need for a spreadsheet in the step below.


Create Zapier flow: Peltarion ←→ Google Sheet

Now let’s set up a flow in Zapier to call the Peltarion model and receive an email notification if the photo can’t be verified.

This is the Zapier flow that you’re going to create:

Complete Zapier workflow
Figure 2. Complete Zapier workflow.
  1. Log in to Zapier.

  2. In the My apps window add a Peltarion connection.
    We’ve pre-trained demo model already. Use the URL and Token below to access our deployed model. You can also build and deploy a car classifier yourself in our car damage classifier tutorial.

  3. In the Zaps window make a Zap.

  4. The first trigger is New Spreadsheet Row in Google Sheets.
    Make sure it triggers whenever a new row is added to your spreadsheet (the one you created in the previous part of the tutorial).

  5. Add action Prediction in Peltarion.
    In the next step of the Zapier flow, call a Peltarion model trained to classify different types of car damage (ours or your own) .

  6. Add filter Only continue if…​ step to sort out the photos where the Peltarion model isn’t confident in its prediction.

    1. Add a Helper app Filter

    2. In Filter Setup & Testing click Only continue if… and select Predictions by Peltarion and then Class confidence.

    3. Choose condition (Number) Less than…

    4. Enter value 1 in the last field.

    5. Press Continue to find out if your prediction would have passed.

  7. Add step that send you and email if a photo couldn’t be verified.
    Search for Email by Zapier and add it (will then show as Action / Send Outbound Email). Enter this info:

    • To: <your mail>

    • Subject: Unverified insurance claim

    • Body: Click in the Body field

      • Select Insert dataNew Spreadsheet Row in Google sheetsPhoto
        This will add a link to the unverified image to the mail.

      • Then add some text like is unverified. Please take a look.

  8. Done!

Verify zap - Recieve a mail from the zap

To verify copy the row below and paste it into you spreadsheet:

Charlie

https://storage.googleapis.com/bucket-8732/Zapier_car_damage_images/CardamageTest.jpg

unknown

Example:

Verification email example
Figure 3. Example email with a link to the photo so the receiver can take a look.

Recap

And that’s it! Your customized verification system is finished. In this tutorial, you learned to:

  1. Build a workflow using apps you already use.

  2. Deploy a Peltarion model in Zapier.

  3. Integrate it into your processes.


Next project

If you’re keen to try out another one of our tutorials that utilize another low-code tool, check out this sales forecasting tutorial using Google Sheets.

Was this page helpful?
YesNo